Development and validation of a machine learning model for predicting intrapartum fever using pre-labor analgesia clinical indicators: a multicenter retrospective study

利用产前镇痛临床指标预测产时发热的机器学习模型的开发与验证:一项多中心回顾性研究

阅读:1

Abstract

BACKGROUND: Labor anesthesia is commonly used for pain relief during labor, but it can increase the risk of intrapartum fever. Currently, there are no reliable tools to predict which parturients might develop fever before labor anesthesia. The prediction model we developed aims to predict the incidence of intrapartum fever before labor analgesia. METHODS: This study retrospectively analyzed the clinical data of parturients who underwent labor analgesia at Chengdu Jinjiang District Maternal & Child Health Hospital and Sichuan Jinxin Xinan Women's & Children's Hospital from January 2021 to June 2023. After the data were processed, the parturients were randomly divided into training and validation cohorts at an 8:2 ratio. The least absolute shrinkage and selection operator method was used for feature selection. Six machine learning models were developed and subjected to comprehensive analysis to assess and validate their predictive capabilities, ultimately selecting the best-performing model. RESULTS: The study included a total of 5,052 parturients, with 418 (8.27%) parturients experiencing intrapartum fever. The predictive factors were primiparity, estimated neonatal weight, degree of uterine dilatation, presence of anemia, number of vaginal examinations, and height. The multilayer perceptron model emerged as the best-performing predictive model, achieving an area under the curve of 0.707, a sensitivity of 0.753, and a specificity of 0.584. CONCLUSIONS: The multilayer perceptron model, utilizing readily available pre-labor analgesia variables, demonstrates potential for predicting intrapartum fever. In comparison to existing tools, this model may enable earlier identification of high-risk parturients, supporting timely interventions and potentially enhancing maternal and neonatal health outcomes.

特别声明

1、本页面内容包含部分的内容是基于公开信息的合理引用;引用内容仅为补充信息,不代表本站立场。

2、若认为本页面引用内容涉及侵权,请及时与本站联系,我们将第一时间处理。

3、其他媒体/个人如需使用本页面原创内容,需注明“来源:[生知库]”并获得授权;使用引用内容的,需自行联系原作者获得许可。

4、投稿及合作请联系:info@biocloudy.com。